Article

Do-Calculus Interventions in Predictive Coding Networks: Formal Correspondence, Empirical Validation, and Architectural Prescriptions for Clinical Causal AI

2026-07-07

Abstract excerpt

<title>Abstract</title> <p>Clinical decision support increasingly demands AI systems capable of reasoning about the consequences of actions rather than merely predicting outcomes from historical patterns. Here we derive a formal correspondence between predictive coding (PC) network dynamics and Pearl's do-calculus. It shows empirically that this correspondence yields a measurable interventional advantage over sta...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: ff2fcef1-93d1-5a1a-b98a-df0590563fe4
DOI: 10.21203/rs.3.rs-10246589/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Do-Calculus Interventions in Predictive Coding Networks: Formal Correspondence, Empirical Validation, and Architectural Prescriptions for Clinical Causal AIDOI 10.21203/rs.3.rs-10246589/v1Read

Causal AI for Data Scientists: A Framework to Automate Discovery of Causal Relationships in Noisy DatasetsSemantic proximity Read

Leveraging Expert Knowledge and Causal Structure Learning to Build Parsimonious Models of Acute Brain Dysfunction in the Pediatric Intensive Care Unit (PICU)Semantic proximity Read

Explainable Artificial Intelligence in Precision Medicine: Methods, Applications, and ChallengesSemantic proximity Read

Medical World Model: From Passive Prediction to Active Simulation in MedicineSemantic proximity Read

Trustworthy personalized treatment selection: causal effect-trees and calibration in perioperative medicineSemantic proximity Read

Modular Differentiable Explanations for Markov Disease Models: A Transparent Framework for Clinical Decision SupportSemantic proximity Read

A formalization of the IdioNomo Framework for explanation and prediction in psychology: unifying idiographic and nomothetic approachesSemantic proximity Read

MedAgent-X: A Multi-Agent Explainable Clinical Decision Support System via Knowledge Graph-Guided Hierarchical Reasoning and Uncertainty-Aware Transformer NetworksSemantic proximity Read

Why Compression Creates Intelligence: The Architecture of Experience in Large ModelsSemantic proximity Read

Empowerment Gain and Causal Model Construction: Children and adults are sensitive to controllability and variability in their causal interventionsSemantic proximity Read